Datasets:

CodeGoat24
/

VideoDPO

Dataset card Data Studio Files Files and versions Community

Split (1)

train · 10k rows

Subsets and Splits

No community queries yet

The top public SQL queries from the community will appear here once available.

prompt stringlengths 4 8.37k	conversations listlengths 2 2	images sequencelengths 16 16
A hallway that seems to stretch and warp.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [A hallway that seems to stretch and warp.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000630/0.png", "losevideos/000630/1.png", "losevideos/000630/2.png", "losevideos/000630/3.png", "losevideos/000630/4.png", "losevideos/000630/5.png", "losevideos/000630/6.png", "losevideos/000630/7.png", "winvideos/000630/0.png", "winvideos/000630/1.png", "winvideos/000630/2.png", "winvideos/000630/3.png", "winvideos/000630/4.png", "winvideos/000630/5.png", "winvideos/000630/6.png", "winvideos/000630/7.png" ]
Ferdowsi reading poetry.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Ferdowsi reading poetry.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004202/0.png", "losevideos/004202/1.png", "losevideos/004202/2.png", "losevideos/004202/3.png", "losevideos/004202/4.png", "losevideos/004202/5.png", "losevideos/004202/6.png", "losevideos/004202/7.png", "winvideos/004202/0.png", "winvideos/004202/1.png", "winvideos/004202/2.png", "winvideos/004202/3.png", "winvideos/004202/4.png", "winvideos/004202/5.png", "winvideos/004202/6.png", "winvideos/004202/7.png" ]
Realistic, personality: [The opening shot is a wide-angle view of a dimly lit room resembling a high-security vault. Stacks of money are piled up against the walls, creating an atmosphere of wealth and greed. The room is filled with an eerie silence, setting the stage for the upcoming heist.]unreal engine, hyper real --q 2 --v 5.2 --ar 16:9.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Realistic, personality: [The opening shot is a wide-angle view of a dimly lit room resembling a high-security vault. Stacks of money are piled up against the walls, creating an atmosphere of wealth and greed. The room is filled with an eerie silence, setting the stage for the upcoming heist.]unreal engine, hyper real --q 2 --v 5.2 --ar 16:9.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007822/0.png", "winvideos/007822/1.png", "winvideos/007822/2.png", "winvideos/007822/3.png", "winvideos/007822/4.png", "winvideos/007822/5.png", "winvideos/007822/6.png", "winvideos/007822/7.png", "losevideos/007822/0.png", "losevideos/007822/1.png", "losevideos/007822/2.png", "losevideos/007822/3.png", "losevideos/007822/4.png", "losevideos/007822/5.png", "losevideos/007822/6.png", "losevideos/007822/7.png" ]
Realistic illustration of a courtroom flooded by lemonade.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Realistic illustration of a courtroom flooded by lemonade.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000289/0.png", "winvideos/000289/1.png", "winvideos/000289/2.png", "winvideos/000289/3.png", "winvideos/000289/4.png", "winvideos/000289/5.png", "winvideos/000289/6.png", "winvideos/000289/7.png", "losevideos/000289/0.png", "losevideos/000289/1.png", "losevideos/000289/2.png", "losevideos/000289/3.png", "losevideos/000289/4.png", "losevideos/000289/5.png", "losevideos/000289/6.png", "losevideos/000289/7.png" ]
an elephant swimming in the ocean.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [an elephant swimming in the ocean.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006823/0.png", "winvideos/006823/1.png", "winvideos/006823/2.png", "winvideos/006823/3.png", "winvideos/006823/4.png", "winvideos/006823/5.png", "winvideos/006823/6.png", "winvideos/006823/7.png", "losevideos/006823/0.png", "losevideos/006823/1.png", "losevideos/006823/2.png", "losevideos/006823/3.png", "losevideos/006823/4.png", "losevideos/006823/5.png", "losevideos/006823/6.png", "losevideos/006823/7.png" ]
woman in white closing the door of her house.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [woman in white closing the door of her house.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/008547/0.png", "winvideos/008547/1.png", "winvideos/008547/2.png", "winvideos/008547/3.png", "winvideos/008547/4.png", "winvideos/008547/5.png", "winvideos/008547/6.png", "winvideos/008547/7.png", "losevideos/008547/0.png", "losevideos/008547/1.png", "losevideos/008547/2.png", "losevideos/008547/3.png", "losevideos/008547/4.png", "losevideos/008547/5.png", "losevideos/008547/6.png", "losevideos/008547/7.png" ]
: a laughing baker is floating in the bakery with flying bread, snadwiches, croissant, colorful neonlights-ar 16:9 -motion 2.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [: a laughing baker is floating in the bakery with flying bread, snadwiches, croissant, colorful neonlights-ar 16:9 -motion 2.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/009469/0.png", "losevideos/009469/1.png", "losevideos/009469/2.png", "losevideos/009469/3.png", "losevideos/009469/4.png", "losevideos/009469/5.png", "losevideos/009469/6.png", "losevideos/009469/7.png", "winvideos/009469/0.png", "winvideos/009469/1.png", "winvideos/009469/2.png", "winvideos/009469/3.png", "winvideos/009469/4.png", "winvideos/009469/5.png", "winvideos/009469/6.png", "winvideos/009469/7.png" ]
Solar system, with shooting stars, ultra HD, cinematic, 3d max, 3:2, 4k resolution,.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Solar system, with shooting stars, ultra HD, cinematic, 3d max, 3:2, 4k resolution,.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002133/0.png", "losevideos/002133/1.png", "losevideos/002133/2.png", "losevideos/002133/3.png", "losevideos/002133/4.png", "losevideos/002133/5.png", "losevideos/002133/6.png", "losevideos/002133/7.png", "winvideos/002133/0.png", "winvideos/002133/1.png", "winvideos/002133/2.png", "winvideos/002133/3.png", "winvideos/002133/4.png", "winvideos/002133/5.png", "winvideos/002133/6.png", "winvideos/002133/7.png" ]
Alex and ben climbed down from the tree and started walking to their village.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Alex and ben climbed down from the tree and started walking to their village.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/001586/0.png", "losevideos/001586/1.png", "losevideos/001586/2.png", "losevideos/001586/3.png", "losevideos/001586/4.png", "losevideos/001586/5.png", "losevideos/001586/6.png", "losevideos/001586/7.png", "winvideos/001586/0.png", "winvideos/001586/1.png", "winvideos/001586/2.png", "winvideos/001586/3.png", "winvideos/001586/4.png", "winvideos/001586/5.png", "winvideos/001586/6.png", "winvideos/001586/7.png" ]
a boy stands in the garage where a band is rehearsing. View from his back.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a boy stands in the garage where a band is rehearsing. View from his back.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/008075/0.png", "winvideos/008075/1.png", "winvideos/008075/2.png", "winvideos/008075/3.png", "winvideos/008075/4.png", "winvideos/008075/5.png", "winvideos/008075/6.png", "winvideos/008075/7.png", "losevideos/008075/0.png", "losevideos/008075/1.png", "losevideos/008075/2.png", "losevideos/008075/3.png", "losevideos/008075/4.png", "losevideos/008075/5.png", "losevideos/008075/6.png", "losevideos/008075/7.png" ]
a fast moving cinematic close up shot of crip gang members doing a drive by shooting on a house in south central LA, bright Sun, palm trees, gang signs, urban, cinematic -motion 3 -gs 16 —fps 24.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a fast moving cinematic close up shot of crip gang members doing a drive by shooting on a house in south central LA, bright Sun, palm trees, gang signs, urban, cinematic -motion 3 -gs 16 —fps 24.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004063/0.png", "winvideos/004063/1.png", "winvideos/004063/2.png", "winvideos/004063/3.png", "winvideos/004063/4.png", "winvideos/004063/5.png", "winvideos/004063/6.png", "winvideos/004063/7.png", "losevideos/004063/0.png", "losevideos/004063/1.png", "losevideos/004063/2.png", "losevideos/004063/3.png", "losevideos/004063/4.png", "losevideos/004063/5.png", "losevideos/004063/6.png", "losevideos/004063/7.png" ]
wide view of a Mom and her 5-year-old ((son)) walking down the street in a USA town on a sunny day, calm atmosphere, natural lighting, line drawing, bold lines, in the style of Ghibli Studio -neg NSFW, photorealistic, 35mm film, deformed, glitch, blurry, noisy, off-center, cross-eyed, closed eyes, bad anatomy, ugly, disfigured, mutated, impressionism, expressionism, oil, acrylic.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [wide view of a Mom and her 5-year-old ((son)) walking down the street in a USA town on a sunny day, calm atmosphere, natural lighting, line drawing, bold lines, in the style of Ghibli Studio -neg NSFW, photorealistic, 35mm film, deformed, glitch, blurry, noisy, off-center, cross-eyed, closed eyes, bad anatomy, ugly, disfigured, mutated, impressionism, expressionism, oil, acrylic.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004269/0.png", "winvideos/004269/1.png", "winvideos/004269/2.png", "winvideos/004269/3.png", "winvideos/004269/4.png", "winvideos/004269/5.png", "winvideos/004269/6.png", "winvideos/004269/7.png", "losevideos/004269/0.png", "losevideos/004269/1.png", "losevideos/004269/2.png", "losevideos/004269/3.png", "losevideos/004269/4.png", "losevideos/004269/5.png", "losevideos/004269/6.png", "losevideos/004269/7.png" ]
A lone figure, a young woman of Hispanic descent, standing on a mountaintop at sunrise, gazing into the distance. The scene is filled with vibrant colors and a sense of awakening and inspiration.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [A lone figure, a young woman of Hispanic descent, standing on a mountaintop at sunrise, gazing into the distance. The scene is filled with vibrant colors and a sense of awakening and inspiration.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002074/0.png", "winvideos/002074/1.png", "winvideos/002074/2.png", "winvideos/002074/3.png", "winvideos/002074/4.png", "winvideos/002074/5.png", "winvideos/002074/6.png", "winvideos/002074/7.png", "losevideos/002074/0.png", "losevideos/002074/1.png", "losevideos/002074/2.png", "losevideos/002074/3.png", "losevideos/002074/4.png", "losevideos/002074/5.png", "losevideos/002074/6.png", "losevideos/002074/7.png" ]
vampire woman.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [vampire woman.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/001504/0.png", "losevideos/001504/1.png", "losevideos/001504/2.png", "losevideos/001504/3.png", "losevideos/001504/4.png", "losevideos/001504/5.png", "losevideos/001504/6.png", "losevideos/001504/7.png", "winvideos/001504/0.png", "winvideos/001504/1.png", "winvideos/001504/2.png", "winvideos/001504/3.png", "winvideos/001504/4.png", "winvideos/001504/5.png", "winvideos/001504/6.png", "winvideos/001504/7.png" ]
anime asian rapper.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [anime asian rapper.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000845/0.png", "winvideos/000845/1.png", "winvideos/000845/2.png", "winvideos/000845/3.png", "winvideos/000845/4.png", "winvideos/000845/5.png", "winvideos/000845/6.png", "winvideos/000845/7.png", "losevideos/000845/0.png", "losevideos/000845/1.png", "losevideos/000845/2.png", "losevideos/000845/3.png", "losevideos/000845/4.png", "losevideos/000845/5.png", "losevideos/000845/6.png", "losevideos/000845/7.png" ]
the indian village boy ramesh and his family laughing and playing in stunning 4K resolution, with detailed 3D animation of Ramesh's family living happy life.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [the indian village boy ramesh and his family laughing and playing in stunning 4K resolution, with detailed 3D animation of Ramesh's family living happy life.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002751/0.png", "winvideos/002751/1.png", "winvideos/002751/2.png", "winvideos/002751/3.png", "winvideos/002751/4.png", "winvideos/002751/5.png", "winvideos/002751/6.png", "winvideos/002751/7.png", "losevideos/002751/0.png", "losevideos/002751/1.png", "losevideos/002751/2.png", "losevideos/002751/3.png", "losevideos/002751/4.png", "losevideos/002751/5.png", "losevideos/002751/6.png", "losevideos/002751/7.png" ]
man flying into the galaxies, trip acid, cartoon realistic.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [man flying into the galaxies, trip acid, cartoon \nrealistic.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/001011/0.png", "losevideos/001011/1.png", "losevideos/001011/2.png", "losevideos/001011/3.png", "losevideos/001011/4.png", "losevideos/001011/5.png", "losevideos/001011/6.png", "losevideos/001011/7.png", "winvideos/001011/0.png", "winvideos/001011/1.png", "winvideos/001011/2.png", "winvideos/001011/3.png", "winvideos/001011/4.png", "winvideos/001011/5.png", "winvideos/001011/6.png", "winvideos/001011/7.png" ]
indian muscular king managing two small brother in kingdom.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [indian muscular king managing two small brother in kingdom.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004967/0.png", "winvideos/004967/1.png", "winvideos/004967/2.png", "winvideos/004967/3.png", "winvideos/004967/4.png", "winvideos/004967/5.png", "winvideos/004967/6.png", "winvideos/004967/7.png", "losevideos/004967/0.png", "losevideos/004967/1.png", "losevideos/004967/2.png", "losevideos/004967/3.png", "losevideos/004967/4.png", "losevideos/004967/5.png", "losevideos/004967/6.png", "losevideos/004967/7.png" ]
fashion show, models facing front only, nature background, camera wide angle, -neg morphing, erratic fluctuation in motion, noisy, bad quality, distorted Aspect ratio:.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [fashion show, models facing front only, nature background, camera wide angle, -neg morphing, erratic fluctuation in motion, noisy, bad quality, distorted\nAspect ratio:.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001748/0.png", "winvideos/001748/1.png", "winvideos/001748/2.png", "winvideos/001748/3.png", "winvideos/001748/4.png", "winvideos/001748/5.png", "winvideos/001748/6.png", "winvideos/001748/7.png", "losevideos/001748/0.png", "losevideos/001748/1.png", "losevideos/001748/2.png", "losevideos/001748/3.png", "losevideos/001748/4.png", "losevideos/001748/5.png", "losevideos/001748/6.png", "losevideos/001748/7.png" ]
A boy A village and ghost fight.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [A boy \nA village \nand ghost fight.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005335/0.png", "losevideos/005335/1.png", "losevideos/005335/2.png", "losevideos/005335/3.png", "losevideos/005335/4.png", "losevideos/005335/5.png", "losevideos/005335/6.png", "losevideos/005335/7.png", "winvideos/005335/0.png", "winvideos/005335/1.png", "winvideos/005335/2.png", "winvideos/005335/3.png", "winvideos/005335/4.png", "winvideos/005335/5.png", "winvideos/005335/6.png", "winvideos/005335/7.png" ]
muscular jesus cruciffied on a wooden cross breaking it with his arms.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [muscular jesus cruciffied on a wooden cross breaking it with his arms.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004112/0.png", "winvideos/004112/1.png", "winvideos/004112/2.png", "winvideos/004112/3.png", "winvideos/004112/4.png", "winvideos/004112/5.png", "winvideos/004112/6.png", "winvideos/004112/7.png", "losevideos/004112/0.png", "losevideos/004112/1.png", "losevideos/004112/2.png", "losevideos/004112/3.png", "losevideos/004112/4.png", "losevideos/004112/5.png", "losevideos/004112/6.png", "losevideos/004112/7.png" ]
atmosphere view with purple birds flyng around and 3 planets -w2 -Size75 Message: Universe is yours (Font: MODERN).	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [atmosphere view with purple birds flyng around and 3 planets -w2 -Size75 Message: Universe is yours (Font: MODERN).]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001802/0.png", "winvideos/001802/1.png", "winvideos/001802/2.png", "winvideos/001802/3.png", "winvideos/001802/4.png", "winvideos/001802/5.png", "winvideos/001802/6.png", "winvideos/001802/7.png", "losevideos/001802/0.png", "losevideos/001802/1.png", "losevideos/001802/2.png", "losevideos/001802/3.png", "losevideos/001802/4.png", "losevideos/001802/5.png", "losevideos/001802/6.png", "losevideos/001802/7.png" ]
Six dragons flying in the clouds and mist.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Six dragons flying in the clouds and mist.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003697/0.png", "winvideos/003697/1.png", "winvideos/003697/2.png", "winvideos/003697/3.png", "winvideos/003697/4.png", "winvideos/003697/5.png", "winvideos/003697/6.png", "winvideos/003697/7.png", "losevideos/003697/0.png", "losevideos/003697/1.png", "losevideos/003697/2.png", "losevideos/003697/3.png", "losevideos/003697/4.png", "losevideos/003697/5.png", "losevideos/003697/6.png", "losevideos/003697/7.png" ]
spawns a hen that carries a kitten around on her back.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [spawns a hen that carries a kitten around on her back.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000732/0.png", "losevideos/000732/1.png", "losevideos/000732/2.png", "losevideos/000732/3.png", "losevideos/000732/4.png", "losevideos/000732/5.png", "losevideos/000732/6.png", "losevideos/000732/7.png", "winvideos/000732/0.png", "winvideos/000732/1.png", "winvideos/000732/2.png", "winvideos/000732/3.png", "winvideos/000732/4.png", "winvideos/000732/5.png", "winvideos/000732/6.png", "winvideos/000732/7.png" ]
a white car -seed 2272183.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a white car -seed 2272183.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002759/0.png", "winvideos/002759/1.png", "winvideos/002759/2.png", "winvideos/002759/3.png", "winvideos/002759/4.png", "winvideos/002759/5.png", "winvideos/002759/6.png", "winvideos/002759/7.png", "losevideos/002759/0.png", "losevideos/002759/1.png", "losevideos/002759/2.png", "losevideos/002759/3.png", "losevideos/002759/4.png", "losevideos/002759/5.png", "losevideos/002759/6.png", "losevideos/002759/7.png" ]
hip hop dancing santa claus,after movements,8k ultra quality -motion 4 -gs 24.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [hip hop dancing santa claus,after movements,8k ultra quality -motion 4 -gs 24.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009945/0.png", "winvideos/009945/1.png", "winvideos/009945/2.png", "winvideos/009945/3.png", "winvideos/009945/4.png", "winvideos/009945/5.png", "winvideos/009945/6.png", "winvideos/009945/7.png", "losevideos/009945/0.png", "losevideos/009945/1.png", "losevideos/009945/2.png", "losevideos/009945/3.png", "losevideos/009945/4.png", "losevideos/009945/5.png", "losevideos/009945/6.png", "losevideos/009945/7.png" ]
create horror look.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [create horror look.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000512/0.png", "losevideos/000512/1.png", "losevideos/000512/2.png", "losevideos/000512/3.png", "losevideos/000512/4.png", "losevideos/000512/5.png", "losevideos/000512/6.png", "losevideos/000512/7.png", "winvideos/000512/0.png", "winvideos/000512/1.png", "winvideos/000512/2.png", "winvideos/000512/3.png", "winvideos/000512/4.png", "winvideos/000512/5.png", "winvideos/000512/6.png", "winvideos/000512/7.png" ]
an epic science fiction ,black and white 1979 film scene, 35mm ,depth of field, establishing shot, night time, dramatic lighting , futuristic flying spaceships slowly flying, the year is 2100, in,4k , high resolution, cinematic -neg “malformed, bad anatomy, disfigured, poorly drawn face, mutation, mutated, extra limb, ugly, disgusting, poorly drawn hands, missing limb, floating limbs, disconnected limbs, malformed hands, bikini, clothes, pants, dresses, skirts, blouse, censored, blurry”.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [an epic science fiction ,black and white 1979 film scene, 35mm ,depth of field, establishing shot, night time, dramatic lighting , futuristic flying spaceships slowly flying, the year is 2100, in,4k , high resolution, cinematic -neg “malformed, bad anatomy, disfigured, poorly drawn face, mutation, mutated, extra limb, ugly, disgusting, poorly drawn hands, missing limb, floating limbs, disconnected limbs, malformed hands, bikini, clothes, pants, dresses, skirts, blouse, censored, blurry”.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006578/0.png", "winvideos/006578/1.png", "winvideos/006578/2.png", "winvideos/006578/3.png", "winvideos/006578/4.png", "winvideos/006578/5.png", "winvideos/006578/6.png", "winvideos/006578/7.png", "losevideos/006578/0.png", "losevideos/006578/1.png", "losevideos/006578/2.png", "losevideos/006578/3.png", "losevideos/006578/4.png", "losevideos/006578/5.png", "losevideos/006578/6.png", "losevideos/006578/7.png" ]
a white horse dancing.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a white horse dancing.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006988/0.png", "losevideos/006988/1.png", "losevideos/006988/2.png", "losevideos/006988/3.png", "losevideos/006988/4.png", "losevideos/006988/5.png", "losevideos/006988/6.png", "losevideos/006988/7.png", "winvideos/006988/0.png", "winvideos/006988/1.png", "winvideos/006988/2.png", "winvideos/006988/3.png", "winvideos/006988/4.png", "winvideos/006988/5.png", "winvideos/006988/6.png", "winvideos/006988/7.png" ]
moviendo el cuerpo.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [moviendo el cuerpo.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009913/0.png", "winvideos/009913/1.png", "winvideos/009913/2.png", "winvideos/009913/3.png", "winvideos/009913/4.png", "winvideos/009913/5.png", "winvideos/009913/6.png", "winvideos/009913/7.png", "losevideos/009913/0.png", "losevideos/009913/1.png", "losevideos/009913/2.png", "losevideos/009913/3.png", "losevideos/009913/4.png", "losevideos/009913/5.png", "losevideos/009913/6.png", "losevideos/009913/7.png" ]
a frankenstein-movement-infused anthropomorphic bunny chases an unseen man through the woods - there is no fear in the eyes of the bunny - shot on 1970s kodak fim bleached by the sun.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a frankenstein-movement-infused anthropomorphic bunny chases an unseen man through the woods - there is no fear in the eyes of the bunny - shot on 1970s kodak fim bleached by the sun.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008143/0.png", "losevideos/008143/1.png", "losevideos/008143/2.png", "losevideos/008143/3.png", "losevideos/008143/4.png", "losevideos/008143/5.png", "losevideos/008143/6.png", "losevideos/008143/7.png", "winvideos/008143/0.png", "winvideos/008143/1.png", "winvideos/008143/2.png", "winvideos/008143/3.png", "winvideos/008143/4.png", "winvideos/008143/5.png", "winvideos/008143/6.png", "winvideos/008143/7.png" ]
crowd watching a ceremony inside a grand Mayan hall with sunlight streaming in, hazy, symmetrical -ar 16:9.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [crowd watching a ceremony inside a grand Mayan hall with sunlight streaming in, hazy, symmetrical -ar 16:9.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006926/0.png", "winvideos/006926/1.png", "winvideos/006926/2.png", "winvideos/006926/3.png", "winvideos/006926/4.png", "winvideos/006926/5.png", "winvideos/006926/6.png", "winvideos/006926/7.png", "losevideos/006926/0.png", "losevideos/006926/1.png", "losevideos/006926/2.png", "losevideos/006926/3.png", "losevideos/006926/4.png", "losevideos/006926/5.png", "losevideos/006926/6.png", "losevideos/006926/7.png" ]
kings death creepy forest A hooded figure with a torch appears walking towards the grave.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [kings death creepy forest A hooded figure with a torch appears walking towards the grave.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007032/0.png", "losevideos/007032/1.png", "losevideos/007032/2.png", "losevideos/007032/3.png", "losevideos/007032/4.png", "losevideos/007032/5.png", "losevideos/007032/6.png", "losevideos/007032/7.png", "winvideos/007032/0.png", "winvideos/007032/1.png", "winvideos/007032/2.png", "winvideos/007032/3.png", "winvideos/007032/4.png", "winvideos/007032/5.png", "winvideos/007032/6.png", "winvideos/007032/7.png" ]
ICE AGE CHARACTERS: Sidand Diego, and Roshan eventually locate the human tribe. Describe the moment when Manny, Sid sloth, Diego tiger, and Roshan sabertooth Showcase the relief and joy in Manny's voice as they successfully complete their mission. Convey the sense of accomplishment and unity among the trio.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [ICE AGE CHARACTERS: Sidand Diego, and Roshan eventually locate the human tribe. Describe the moment when Manny, Sid sloth, Diego tiger, and Roshan sabertooth Showcase the relief and joy in Manny's voice as they successfully complete their mission. Convey the sense of accomplishment and unity among the trio.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001666/0.png", "winvideos/001666/1.png", "winvideos/001666/2.png", "winvideos/001666/3.png", "winvideos/001666/4.png", "winvideos/001666/5.png", "winvideos/001666/6.png", "winvideos/001666/7.png", "losevideos/001666/0.png", "losevideos/001666/1.png", "losevideos/001666/2.png", "losevideos/001666/3.png", "losevideos/001666/4.png", "losevideos/001666/5.png", "losevideos/001666/6.png", "losevideos/001666/7.png" ]
a boy playing an innovative electronic educational toy.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a boy playing an innovative electronic educational toy.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/005459/0.png", "winvideos/005459/1.png", "winvideos/005459/2.png", "winvideos/005459/3.png", "winvideos/005459/4.png", "winvideos/005459/5.png", "winvideos/005459/6.png", "winvideos/005459/7.png", "losevideos/005459/0.png", "losevideos/005459/1.png", "losevideos/005459/2.png", "losevideos/005459/3.png", "losevideos/005459/4.png", "losevideos/005459/5.png", "losevideos/005459/6.png", "losevideos/005459/7.png" ]
A picture with a large mountain of dollars with the caption “When work doesn’t bring profit...”.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [A picture with a large mountain of dollars with the caption “When work doesn’t bring profit...”.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002512/0.png", "losevideos/002512/1.png", "losevideos/002512/2.png", "losevideos/002512/3.png", "losevideos/002512/4.png", "losevideos/002512/5.png", "losevideos/002512/6.png", "losevideos/002512/7.png", "winvideos/002512/0.png", "winvideos/002512/1.png", "winvideos/002512/2.png", "winvideos/002512/3.png", "winvideos/002512/4.png", "winvideos/002512/5.png", "winvideos/002512/6.png", "winvideos/002512/7.png" ]
cute boy 3d cartoon Pixar style in' realistic 3D painting style digital art digital art, 8k, 8k resolution, sharp focus, perfect composition, , Jean-Baptiste Monge style, bright, beautiful , splash, real perfect composition, digital art, amazing real hair, unreal engineSony A7R IV, greg , Glittering , cute and adorable, filigree, , rim lighting, lights, extremely , magic, surreal, fantasy, digital art, , wlop, artgerm and james jean, , Miki Asai Macro photography, close-up, hyper detailed, trending on artstation, sharp focus, studio photo, intricate details, highly detailed, by greg rutkowski.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [cute boy \n3d cartoon Pixar style in' realistic 3D painting style \ndigital art\ndigital art, \n 8k, 8k resolution, sharp focus, perfect composition, \n, Jean-Baptiste Monge style, bright, beautiful , splash, real perfect composition, digital art, amazing real hair, unreal engineSony A7R IV, greg\n\n, Glittering , cute and adorable, filigree, , rim lighting, lights, extremely , magic, surreal, fantasy, digital art, , wlop, artgerm and james jean, , Miki Asai Macro photography, close-up, hyper detailed, trending on artstation, sharp focus, studio photo, intricate details, highly detailed, by greg rutkowski.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005624/0.png", "losevideos/005624/1.png", "losevideos/005624/2.png", "losevideos/005624/3.png", "losevideos/005624/4.png", "losevideos/005624/5.png", "losevideos/005624/6.png", "losevideos/005624/7.png", "winvideos/005624/0.png", "winvideos/005624/1.png", "winvideos/005624/2.png", "winvideos/005624/3.png", "winvideos/005624/4.png", "winvideos/005624/5.png", "winvideos/005624/6.png", "winvideos/005624/7.png" ]
a miniature house -seed 8555473.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a miniature house -seed 8555473.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006632/0.png", "losevideos/006632/1.png", "losevideos/006632/2.png", "losevideos/006632/3.png", "losevideos/006632/4.png", "losevideos/006632/5.png", "losevideos/006632/6.png", "losevideos/006632/7.png", "winvideos/006632/0.png", "winvideos/006632/1.png", "winvideos/006632/2.png", "winvideos/006632/3.png", "winvideos/006632/4.png", "winvideos/006632/5.png", "winvideos/006632/6.png", "winvideos/006632/7.png" ]
The camera pans down from a high place, a man is on the top of the mountain,-camera pan down.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [The camera pans down from a high place, a man is on the top of the mountain,-camera pan down.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008864/0.png", "losevideos/008864/1.png", "losevideos/008864/2.png", "losevideos/008864/3.png", "losevideos/008864/4.png", "losevideos/008864/5.png", "losevideos/008864/6.png", "losevideos/008864/7.png", "winvideos/008864/0.png", "winvideos/008864/1.png", "winvideos/008864/2.png", "winvideos/008864/3.png", "winvideos/008864/4.png", "winvideos/008864/5.png", "winvideos/008864/6.png", "winvideos/008864/7.png" ]
water dripping on concrete -pg 15 Message: OVRSTITCH (Font: MODERN).	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [water dripping on concrete -pg 15 Message: OVRSTITCH (Font: MODERN).]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006408/0.png", "winvideos/006408/1.png", "winvideos/006408/2.png", "winvideos/006408/3.png", "winvideos/006408/4.png", "winvideos/006408/5.png", "winvideos/006408/6.png", "winvideos/006408/7.png", "losevideos/006408/0.png", "losevideos/006408/1.png", "losevideos/006408/2.png", "losevideos/006408/3.png", "losevideos/006408/4.png", "losevideos/006408/5.png", "losevideos/006408/6.png", "losevideos/006408/7.png" ]